Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1790 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1176687 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.1448. Min Act: -0.0000

Data Index: 58848 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1664436 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.2057. Min Act: -0.0000

Data Index: 197172 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9637. Min Act: -0.0000

Data Index: 212135 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0972. Min Act: -0.0000

Data Index: 846068 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9224. Min Act: -0.0000

Data Index: 305204 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8936. Min Act: -0.0000

Data Index: 327614 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1108126 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1451775 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8919. Min Act: -0.0000

Data Index: 40472 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1350380 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1139564 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1278058 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1165867 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1256811 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1472119 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8085. Min Act: -0.0000

Data Index: 669702 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1372160 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7194. Min Act: -0.0000

Data Index: 664018 (The Pile)

Max Activating Token Index: 174